Development Claude Code skills

Guides Claude through designing and generating a working MCP server, the official first-party recipe for wrapping an API as agent tools.

First-party skill for driving and testing a running web app in a browser, verifying behavior instead of assuming it from code.

Loads current Claude API reference (model IDs, tool use, streaming, batches, structured outputs) per language, auto-activates when code imports the anthropic SDK, and /claude-api migrate upgrades code to newer models.

Anthropic's dev-workflow set: end-to-end feature development workflow, git commit commands, and a toolkit for building Claude Code plugins themselves.

Reference for building on the Claude API and Anthropic SDK: model IDs, pricing, streaming, tool use, MCP, caching, token counting, and model migration.

Agent that refines code for clarity, consistency, and maintainability without changing behavior.

Modernize legacy codebases (COBOL, old Java/C++/.NET, monoliths) via a structured assess/map/extract-rules/transform/harden workflow, including cross-stack rewrites and version uplifts.

Development kit for building applications with the Claude Agent SDK.

Skills for designing MCP servers that work well with Claude: deployment models (remote HTTP, MCPB, local), tool design patterns, auth, and interactive MCP apps.

Connect Claude to a private MCP server through an Anthropic MCP tunnel; drives the Docker Compose quickstart end to end (certificates, proxy, cloudflared).

One-command onboarding for the Code-with-Claude Makers Cardputer: clones the build-with-claude repo, flashes UIFlow firmware, and installs the Claude Buddy app on an M5Stack Cardputer-Adv.

TypeScript/JavaScript language server integration for enhanced code intelligence in Claude Code.

Python language server (Pyright) for type checking and code intelligence in Claude Code.

Rust language server (rust-analyzer) for code intelligence and analysis in Claude Code.

Go language server (gopls) for code intelligence and refactoring in Claude Code.

C/C++ language server (clangd) for code intelligence in Claude Code.

Java language server (Eclipse JDT.LS) for code intelligence in Claude Code.

C# language server for code intelligence in Claude Code.

Kotlin language server for code intelligence in Claude Code.

Swift language server (SourceKit-LSP) for code intelligence in Claude Code.

Ruby language server for code intelligence and analysis in Claude Code.

PHP language server (Intelephense) for code intelligence in Claude Code.

Lua language server for code intelligence in Claude Code.

Enforces the RED-GREEN-REFACTOR cycle for any feature or bugfix, with a reference of testing anti-patterns to avoid.

4-phase root-cause process for any bug or test failure before proposing fixes, including root-cause tracing, defense-in-depth, and condition-based-waiting techniques.

Sets up parallel development branches via git worktrees so multiple lines of work can proceed without stepping on each other.

Test-driven development methodology adapted to Claude Code sessions.

Builds evaluation harnesses to back the verification loop with measurable pass/fail gates.

Cross-language coding best practices applied during generation and review.

Go idioms and best practices; paired with golang-testing for Go test patterns, TDD, and benchmarks.

Python idioms and best practices for writing production Python.

Python testing patterns with pytest.

C++ standards based on the C++ Core Guidelines; cpp-testing covers GoogleTest and CMake/CTest patterns.

Server-side architecture patterns: APIs, databases, and caching for Node.js/Express/Next.js backends.

React and Next.js frontend patterns for component structure and data flow.

REST API design: resource naming, status codes, pagination, filtering, error responses, versioning, rate limiting.

Playwright end-to-end testing patterns including the Page Object Model.

PostgreSQL optimization patterns for schema and query work.

ClickHouse analytics and data-engineering patterns.

Safe migration patterns across Prisma, Drizzle, Django, and Go migration tooling.

CI/CD, Docker, health checks, and rollback patterns for shipping to production.

Docker Compose, networking, volumes, and container security patterns.

Django models/views/architecture patterns; companion skills cover django-security, django-tdd, and django-verification.

Laravel architecture patterns; companion skills cover laravel-security, laravel-tdd, and laravel-verification.

Java Spring Boot patterns; companion skills cover springboot-security, springboot-tdd, and springboot-verification, plus java-coding-standards and jpa-patterns.

Java Quarkus patterns; companion skills cover quarkus-security, quarkus-tdd, and quarkus-verification.

Modern Perl 5.36+ idioms; companion skills cover perl-security (taint mode) and perl-testing (Test2::V0 TDD).

Production ML engineering workflow: data contracts, evals, deployment, and monitoring.

LLM cost optimization and model-routing patterns for pipelines; content-hash-cache-pattern adds SHA-256 content-hash caching.

Decision framework for choosing regex versus LLM parsing on structured text.

Write-time code-quality enforcement using Plankton hooks.

Gives the agent a real debugger with breakpoints, stepping, variable inspection, and stack traces instead of print-debugging.

General-purpose browser automation with Playwright for scraping, form filling, and end-to-end checks.

Semantic code intelligence via LSP: safe renames, refactors, impact analysis, and verification across a codebase.

Operate Qdrant vector databases: search operations, performance tuning, deployment, and upgrades.

Generate editable AWS architecture diagrams with verified service icons and multiple export formats.

Run safe read-only SQL queries against PostgreSQL databases with multi-connection support.

HashiCorp-maintained skills for Terraform workflows and infrastructure automation.

Extract and analyze HTTP traffic from Charles Proxy session files for API debugging.

Vercel's React and Next.js performance rules (rendering, data fetching, bundle hygiene) applied while the agent writes or reviews code.

Gives the agent a driveable headless browser (navigate, click, fill, screenshot) for testing and inspecting live web pages from the CLI.

Microsoft's official guidance for building on Azure AI Foundry: models, agents, and deployments via the azure-skills repo.

Analyzes an existing codebase's structure and proposes concrete refactors toward better module boundaries and dependency direction.

Official Supabase rules for Postgres schema design, RLS policies, indexing, and query patterns when building on Supabase.

Official shadcn/ui skill for installing, composing, and theming registry components correctly instead of hand-rolling lookalikes.

Official Firebase skill covering project setup, SDK integration, and core service usage for apps built on Firebase.

Official Sentry skill for instrumenting apps and managing releases, sourcemaps, and issues through the Sentry CLI.

Deploys the current project to Vercel with correct project linking and configuration from the CLI.

Official browser-use skill: autonomous browser automation (navigate, interact, extract) driven by the agent.

Microsoft's official Playwright CLI skill for scripting browser automation and end-to-end tests.

Runs a structured code review pass checking security, logic, performance, and style; Agensi's most-installed skill.

Systematically diagnoses why a project will not start: env vars, versions, ports, and dependency mismatches.

Reviews database migration files for destructive or locking operations before they reach production.

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

Cisco IOS and IOS-XE review patterns for show commands, config hierarchy, wildcard masks, ACL placement, interface hygiene, and safe change-window verification.

Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns.

Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate).

Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.

Patterns for robust error handling across TypeScript, Python, and Go. Covers typed errors, error boundaries, retries, circuit breakers, and user-facing error messages.

Git workflow patterns including branching strategies, commit conventions, merge vs rebase, conflict resolution, and collaborative development best practices for teams of all sizes.

GitHub repository operations, automation, and management. Issue triage, PR management, CI/CD operations, release management, and security monitoring using the gh CLI. Use when the user wants to manage GitHub issues, PRs, CI status, releases, contributors, stal

Readiness checklist for homelab VLAN segmentation, local DNS filtering, and WireGuard-style remote access before changing router, firewall, DHCP, or VPN configuration.

Practical home and homelab network planning for gateways, switches, access points, IP ranges, DHCP reservations, DNS, cabling, and common beginner mistakes.

Pi-hole installation, blocklist management, DNS-over-HTTPS setup, DHCP integration, local DNS records, and troubleshooting broken DNS resolution on a home network.

Segmenting home networks into VLANs for IoT, guest, trusted, and server traffic using UniFi, pfSense/OPNsense, and MikroTik : including switch trunk config, firewall rules, and wireless SSID mapping.

WireGuard VPN server setup, peer configuration, key generation, split tunneling vs full tunnel routing, and remote access to a home network from mobile and laptop clients.

Build MCP servers with Node/TypeScript SDK : tools, resources, prompts, Zod validation, stdio vs Streamable HTTP. Use Context7 or official MCP docs for latest API.

当需要调试 Modbus RTU（串口）或 Modbus TCP（网络）设备通信时使用，支持寄存器读写、从站扫描和持续监控。

> Modbus industrial protocol implementation in Rust, Go, and Python. Trigger: modbus, plc, scada, industrial protocol, registers, coils

Safe Python Netmiko patterns for read-only collection, bounded batch SSH, TextFSM parsing, guarded config changes, timeouts, and network automation error handling.

Diagnostics-only BGP troubleshooting patterns for neighbor state, route exchange, prefix policy, AS path inspection, and safe evidence collection.

Pre-deployment checks for router and switch configuration, including dangerous commands, duplicate addresses, subnet overlaps, stale references, management-plane risk, and IOS-style security hygiene.

Diagnose interface errors, drops, CRCs, duplex mismatches, flapping, speed negotiation issues, and counter trends on routers, switches, and Linux hosts.

Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.

Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.

React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.

React and Next.js performance optimization patterns adapted from Vercel Engineering's React Best Practices (https://github.com/vercel-labs/agent-skills). Organizes 70+ rules across 8 priority categories : waterfalls, bundle size, server-side, client fetching,

React component testing with React Testing Library, Vitest/Jest, MSW for network mocking, accessibility assertions with axe, and the decision boundary between component tests and Playwright/Cypress end-to-end runs. Use when writing or fixing tests for React co